DETAILED ACTION
Notice of Pre-AIA or AIA Status
The present application, filed on or after March 16, 2013, is being examined under the first inventor to file provisions of the AIA .
Status of the Claims
Claims 1, 12 and 20 have been amended and claims 2-4 and 12-15 are canceled. Claims 1, 5-12 and 16-20 are pending.
Claim Rejections - 35 USC § 112
The following is a quotation of the first paragraph of 35 U.S.C. 112(a):
(a) IN GENERAL.—The specification shall contain a written description of the invention, and of the manner and process of making and using it, in such full, clear, concise, and exact terms as to enable any person skilled in the art to which it pertains, or with which it is most nearly connected, to make and use the same, and shall set forth the best mode contemplated by the inventor or joint inventor of carrying out the invention.
The following is a quotation of the first paragraph of pre-AIA 35 U.S.C. 112:
The specification shall contain a written description of the invention, and of the manner and process of making and using it, in such full, clear, concise, and exact terms as to enable any person skilled in the art to which it pertains, or with which it is most nearly connected, to make and use the same, and shall set forth the best mode contemplated by the inventor of carrying out his invention.
Claims 1, 12 and 20 are rejected under 35 U.S.C. 112(a) or 35 U.S.C. 112 (pre-AIA ), first paragraph, as failing to comply with the written description requirement. The claim(s) contains subject matter which was not described in the specification in such a way as to reasonably convey to one skilled in the relevant art that the inventor or a joint inventor, or for applications subject to pre-AIA 35 U.S.C. 112, the inventor(s), at the time the application was filed, had possession of the claimed invention.
Independent claims disclose limitation – “: in response to a parameter of the plug-in is not determined based on the first query information and the memory information”.
Any negative limitation or exclusionary proviso must have basis in the original disclosure. If alternative elements are positively recited in the specification, they may be explicitly excluded in the claims. See In re Johnson, 558 F.2d 1008, 1019, 194 USPQ 187, 196 (CCPA 1977) ([the] specification, having described the whole, necessarily described the part remaining). See also Ex parte Grasselli, 231 USPQ 393 (Bd. App. 1983), aff d mem., 738 F.2d 453 (Fed. Cir. 1984). The mere absence of a positive recitation is not basis for an exclusion. Any claim containing a negative limitation which does not have basis in the original disclosure should be rejected under 35 U.S.C. 112(a) or pre-AIA 35 U.S.C. 112, first paragraph, as failing to comply with the written description requirement. Note that a lack of literal basis in the specification for a negative limitation may not be sufficient to establish a prima facie case for lack of descriptive support. Ex parte Parks, 30 USPQ2d 1234, 1236 (Bd. Pat. App. & Inter. 1993). See MPEP 2163 - 2163.07(b) for a discussion of the written description requirement of 35 U.S.C. 112(a) and pre-AIA 35 U.S.C. 112, first paragraph.
Although the limitation is based on paragraph [0068], there is no explicit disclosure of the “plug-in is not determined.” Such functionality is only an assumption, which is not an original disclosure. I.e. “querying the user may include guiding the user to answer a question and obtain clarification of the parameter of the plug-in” is not analogous to the claimed limitation – “querying the user may include guiding the user to answer a question and obtain clarification of the parameter of the plug-in.”
The dependent claims further carry the same deficiency and likewise rejected.
Claim Rejections - 35 USC § 103
The following is a quotation of 35 U.S.C. 103 which forms the basis for all obviousness rejections set forth in this Office action:
A patent for a claimed invention may not be obtained, notwithstanding that the claimed invention is not identically disclosed as set forth in section 102, if the differences between the claimed invention and the prior art are such that the claimed invention as a whole would have been obvious before the effective filing date of the claimed invention to a person having ordinary skill in the art to which the claimed invention pertains. Patentability shall not be negated by the manner in which the invention was made.
Claims 1, 12 and 20, is/are rejected under 35 U.S.C. 103 as being unpatentable over Vishnoi et al. (US 20200342850) in view of Bell et al. (US 2024/0406166).
Regarding claim 1, Vishnoi teaches a computer-implemented method for information processing
determining memory information related to the first query information, wherein the memory information is obtained based on a dialogue content retrieved from a historical dialogue of the user that matches the first query information ([0148], [0218]);
determining, based on the first query information and the memory information, a target tool for processing the first query information from a plurality of candidate tools ([0066], [0161]), wherein the target tool is in a form of a plug-in ([0025] “These subsystems may be implemented as pluggable units”, [0048], [0092], [0181]), and wherein the determining of the target tool comprises:
in response to a parameter of the plug-in is not determined based on the first query information ([0061] “user asks for help or orientation; and … user input that doesn't match well with the Exit and Help intents … enables the master bot to select a particular skill bot for handling an utterance”, [0063] “If there is no specific or explicit invocation … the digital assistant evaluates the received user input”; “ then selects, from the identified candidates, a particular system intent or a skill bot for further handling of the user input utterance”) and the memory information ([0148]), obtaining second query information for clarifying the parameter of the plug-in provided by a user, by invoking a clarification tool among the plurality of candidate tools for actively initiating an interaction with the user ([0089], [0146]-[0147], [0149], [0154]-[0159], [0199]); and
determining the target tool based on the second query information ([0147], [0149]);
invoking the target tool to obtain auxiliary information, wherein the auxiliary information includes data returned after the target tool is invoked ([0047], [0087], [0185]-[[0187]); and generating, based on the first query information and the auxiliary information, a result of processing the first query information ([0140]-[0147]).
Vishnoi does not explicitly teach, however Bell discloses information processing based on a large language model ([0111], [0156], [0164]).
It would have been obvious to one of ordinary skill in the art before the effective filing date of the claimed invention to modify the teachings of Vishnoi to include the LLM as disclosed by Bell. Doing so would allow users of the application to more effectively and efficiently interact with a data source by using natural language prompts to cause operations that would otherwise require multiple user inputs to a plurality of different user interface elements (Bell [0112]).
Claims 1, 5-9, 11-12, 16-17, 19-20, is/are rejected under 35 U.S.C. 103 as being unpatentable over Du et al. (US 20250337701) in view of Poirier et al. (US 20240202539), Gelfenbeyn et al. (US 20170300831) and in further view of Li et al. (US 20250298827).
Regarding claim 1, Du teaches a computer-implemented method for information processing based on a large language model, comprising:
obtaining first query information provided by a user ([0091], [0143]);
determining memory information related to the first query information ([0084], [0124]),
wherein the memory information is obtained based on a dialogue content retrieved from a historical dialogue of the user that matches the first query information (F1C:157, [0084], [0096], [0137], [0146], [0161]);
determining, based on the first query information and the memory information ([0084] “conversation history is used by the chatbots when user prompts (e.g., questions) are routed to the chatbots”, [0161]), a target tool for processing the first query information from a plurality of candidate tools (0092] “sends the user prompt to a selected group of chatbots”; “request can include … context of previous user prompts and responses in the conversation”, [0093] “select, from among the identified set of chatbots … a set of chatbots to receive the user prompt”; [0097] “may send each subsequent prompt to a smaller number of chatbots … that … are most likely to provide the answer needed”, [0170], [0176]),
wherein the target tool is in a form of third-party module
wherein the determining of the target tool comprises:
obtaining second query information for clarifying the parameter ([0088], [0134], [0137], [0147]) of the third-party module significantly … follow up with additional questions to clarify and identify the reason for the difference” [0088], and “may include information that can clarify what users intend … may specify that a visualization should be included, or that data should be ordered in a particular way” [0137], “parameters such as the data set used, the custom instructions provided with user prompts … the format and preferences for answers” [0134], “specify the parameters for the visualization, such as the type of visualization” [0147]); and
determining the target tool based on the second query information ([0095], [0097], [0162]) (see NOTE);
invoking the target tool to obtain auxiliary information ([0119], [0123], [0127], [0162]),
wherein the auxiliary information includes data returned after the target tool is invoked ([0157]); and
generating, based on the first query information and the auxiliary information, a result of processing the first query information ([0133], [0160]).
NOTE - Du teaches multiple rounds of interactions and obtaining additional information needed to and iteratively disambiguating user’s input (aka second query) and asking follow-up questions (aka second queries), based on which the top chatbots are selected. Which is construed to be analogous to the limitation determining the target tool based on the second query information.
However, to further obviate such teachings Poirier discloses determining the target tool based on the second query information ([0184], [0186] “artificial intelligence system selects, based on the interpretation of the query, a first agent of a plurality of different agents”, [0193], [0198]-[0199]).
It would have been obvious to one of ordinary skill in the art at the time of invention to modify the teachings of Du to determining the target tool based on the second query information as disclosed by Poirier. Doing so supports efficient search capabilities is further complicated in circumstances that require subject matter expertise or context specific knowledge (Poirier [0022]).
Du does not explicitly teach the target tool is in a form of a plug-in. Instead Du teaches – “chatbots 108a-108n [-target tools-] can be provided by the computer system 110 or other systems, including third-party systems” [0082], wherein “Each chat bot 108a-108n can have an associated dataset … can also have a corresponding AI/ML model 132 … also have a corresponding set of settings and customizations” [0083], wherein “administrators may add new chat bots or remove existing chatbots” [0086], “chatbots 108a-108n can each separately and independently act on their respective requests in parallel” [0099], “saving the chatbot can include registering the chatbot with a number of different applications, web pages, web applications, or other services” [0116]. However, it is reasonable to conclude that an independently act module, with a separate dataset and customizations, provided by a third-party system is obviously analogous to a plug-in. Therefore, the claim limitation of the target tool is in a form of a plug-in not explicitly recited in Du are implicit.
However, to further obviate such teachings Gelfenbeyn discloses - “the tool is in a form of a plug-in ([0014]) (see NOTE) that has its corresponding parameter” ([0026]), “querying the user, so as to guide the user to provide clarification of the parameter of the plug-in ([0014]), and wherein the tool is determined based on the clarification of the parameter” (F8:882B, [0141], [0145]).
Gelfenbeyn further discloses - wherein the auxiliary information includes data returned after the tool is invoked (F7:758, 760).
It would have been obvious to one of ordinary skill in the art at the time of invention to modify the teachings of Du to include tool with corresponding parameter, query user for a clarification and returning auxiliary information after the tool is invoked as disclosed by Gelfenbeyn. Doing so ensures the alternative agent is likely able to generate responsive content (Gelfenbeyn [0099]).
NOTE - With respect to the “plug-in tool”, Gelfenbeyn discloses –
“an “agent” references one or more computing devices and/or software that is separate from an automated assistant. In some situations, an agent may be a third-party (3P) agent, in that it is managed by a party that is separate from a party that manages the automated assistant. … the agent can be an application installed on the client device or an application executable remote from the client device, but “streamable” on the client device. When the application is invoked, it can be executed by the client device and/or brought to the forefront by the client device (e.g., its content can take over a display of the client device)” [0014].
Although, not explicitly called being “plug-in” the agent functionality that is “separate from an automated assistant”, managed by a third-party, an application installed on the client device or an application executable remote from the client device, meets a definition for the plug-in (i.e. a plug-in is a software component that adds specific features or functionality to an existing program without changing the program's core code). Therefore, an agent shown by Gelfenbeyn in paragraph [0014] is a plug-in tool.
◊ Du does not explicitly teach however Li discloses - wherein the determining of the target tool comprises: in response to a parameter of the plug-in ([0049], [0079], [0083]-[0084]) is not determined based on the first query information ([0084]-[0085] “if the predetermined condition is not satisfied”, “ if the search keyword does not accurately hit”, [0087]-[0088], [0090]) and the memory information ([0067]-[0069], [0106]), obtaining second query information for clarifying the parameter of the plug-in provided by a user, by invoking a clarification tool among the plurality of candidate tools for actively initiating an interaction with the user ([0109]).
It would have been obvious to one of ordinary skill in the art at the time of invention to modify the teachings of Du to determine the target tool in response to a parameter of the plug-in as disclosed by Li. Doing so improves the matching rate with the user's search intent and conversion rate of book recommendation and the user retention (Li [0114]-[0115])
Regarding claims 5 and 16, Du as modified teaches the method and the device, wherein the target tool comprises a retrieval tool, and the invoking of the target tool to obtain the auxiliary information comprises:
invoking the retrieval tool to retrieve data resources to obtain reference information for answering the first query information (Du [0117]-[0119], Poirier [0033], [0038]-[0039]).
Regarding claim 6, Du as modified teaches the method according to claim 5, wherein the invoking of the retrieval tool to retrieve the data resources to obtain the reference information for answering the first query information comprises:
invoking a first retriever to retrieve business data comprising a plurality of business documents to obtain at least one target business document associated with the first query information (Du [0119], [0127], [0176]-[0177], Poirier [0033] “data domains (e.g., documents, tabular data, insights derived from artificial intelligence applications, web content, or other data sources) of an enterprise. Enterprise domains may also include industry-specific domains (e.g., healthcare domain, defense domain, etc.)”, [0067]),
wherein the first retriever supports multimodal data retrieval (Du [0075], Poirier [0248], [0255]), and the at least one target business document is ranked according to a predetermined ranking strategy (Poirier [0093] “assign relevance scores … for each of the retrieved data records … filter out data records that have a relevance score below a configurable threshold value … define that a maximum of 50 data records can be returned”, [0094], [0146] “best results, ranked results”).
Regarding claim 7, Du as modified teaches the method according to claim 5, wherein the invoicing of the retrieval tool to retrieve the data resources to obtain the reference information for answering the first query information comprises: invoking a second retriever to retrieve news information data comprising a plurality of news information entries to obtain at least one target news information entry associated with the first query information (Poirier [0033] “external domains that are external to the enterprise, such news sources, weather sources, and the like”, [0069]).
Regarding claim 8, Du as modified teaches the method according to claim 6, wherein the retrieval is performed based on a transformed retrieval element, and wherein the retrieval element includes a keyword (Du [0072], [0082], [0095], Poirier [0194], [0195], [0237]) and/or semantics corresponding to the first query information (Du [0118], [0135], Poirier [0116]-[0117], [0202]).
Regarding claims 9 and 17, Du as modified teaches the method and the device, further comprising:
determining, based on the obtained auxiliary information, whether the tool has been correctly invoked (Du [0073], [0088], [0167], Poirier [0135] “validate large language model outputs. The artificial intelligence traceability module may also determine a compatibility of the different sources”, [0241], [0244], [0250]); and
redetermining a new tool for processing the query information selecting … based on a processed input, one or more agent of a plurality of different agents(Poirier [0153]).
Poirier does not explicitly teach, however Gelfenbeyn discloses in response to determining that the tool has not been correctly invoked, redetermining a new tool for processing the query information ([0010 “failed attempt to utilize an agent to perform the intent, which is then followed by invoking an alternative agent in another attempt to perform the intent”, [0099]).
It would have been obvious to one of ordinary skill in the art at the time of invention to modify the teachings of Poirier to include determining that the tool has not been correctly invoked as disclosed by Gelfenbeyn. Doing so ensures the alternative agent is likely able to generate responsive content (Gelfenbeyn [0099]).
NOTE in alternative art US 20250053835 likewise disclose claims 9 and 17 in [0022] and US 20220028378 likewise disclose claims 9 and 17 in [0036] and further obviate the teaching of Du.
Regarding claims 11 and 19, Du as modified teaches the method and the device, wherein the method is performed based on a large language model trained by supervised fine-tuning (Poirier [0128], [0137]-[0138], [0144], [0147]).
Claim 20 recites substantially the same limitations as claim 1 and is rejected for substantially the same reasons.
Claims 10 and 18 is/are rejected under 35 U.S.C. 103 as being unpatentable over Du in view of Jernigan et al. (US 20180365026).
Regarding claims 10 and 18, Du as modified does not explicitly teach, however Jernigan discloses the method and the device, further comprising:
storing, in a predetermined amount of memory for a current dialogue, the memory information related to the query information and the auxiliary information obtained from the invoking of the tool ([0100]-[0102]).
It would have been obvious to one of ordinary skill in the art at the time of invention to modify the teachings of Du to include a predetermined amount of memory for a current dialogue as disclosed by Jernigan. Doing so would improve accuracy of responses of the virtual assistant (Jernigan [0006], [0022]).
Response to Arguments
Applicant's arguments, filed 07/14/2026, in regard to the presently amended claims are addressed in the updated rejections to the claims above.
Conclusion
Applicant's amendment necessitated the new ground(s) of rejection presented in this Office action. Accordingly, THIS ACTION IS MADE FINAL. See MPEP § 706.07(a). Applicant is reminded of the extension of time policy as set forth in 37 CFR 1.136(a).
A shortened statutory period for reply to this final action is set to expire THREE MONTHS from the mailing date of this action. In the event a first reply is filed within TWO MONTHS of the mailing date of this final action and the advisory action is not mailed until after the end of the THREE-MONTH shortened statutory period, then the shortened statutory period will expire on the date the advisory action is mailed, and any nonprovisional extension fee (37 CFR 1.17(a)) pursuant to 37 CFR 1.136(a) will be calculated from the mailing date of the advisory action. In no event, however, will the statutory period for reply expire later than SIX MONTHS from the mailing date of this final action.
Any inquiry concerning this communication or earlier communications from the examiner should be directed to POLINA G PEACH whose telephone number is (571)270-7646. The examiner can normally be reached Monday-Friday, 9:30 - 5:30.
Examiner interviews are available via telephone, in-person, and video conferencing using a USPTO supplied web-based collaboration tool. To schedule an interview, applicant is encouraged to use the USPTO Automated Interview Request (AIR) at http://www.uspto.gov/interviewpractice.
If attempts to reach the examiner by telephone are unsuccessful, the examiner’s supervisor, Aleksandr Kerzhner can be reached at 571-270-1760. The fax phone number for the organization where this application or proceeding is assigned is 571-273-8300.
Information regarding the status of published or unpublished applications may be obtained from Patent Center. Unpublished application information in Patent Center is available to registered users. To file and manage patent submissions in Patent Center, visit: https://patentcenter.uspto.gov. Visit https://www.uspto.gov/patents/apply/patent-center for more information about Patent Center and https://www.uspto.gov/patents/docx for information about filing in DOCX format. For additional questions, contact the Electronic Business Center (EBC) at 866-217-9197 (toll-free). If you would like assistance from a USPTO Customer Service Representative, call 800-786-9199 (IN USA OR CANADA) or 571-272-1000.
/POLINA G PEACH/Primary Examiner, Art Unit 2165 July 25, 2026
Prosecution Insights